Evidaxis

SAELens

repo
Unassigned (AI-v1 census) · n = 5778 · decoderesearch/SAELens
1 of 3 axes measurable · conf low
convergence gate
Convergence gate: Gate: not computable — history 1 of 4 weekly observations Development velocity: measured × Citation momentum: not measurable ∅ Direct-dependents momentum (deps.dev): not measurable ∅
gate
0 of 3 axes

Gate: not computable — history 1 of 4 weekly observations

Gate: not computable — history 1 of 4 weekly observations
position in cohort distribution one of 5778 in cohort
percentile 86 within cohort p25 p50 p75 p0 p100
percentile
p86
momentum averages present-axis z-scores; two- and three-axis scores are not strictly comparable
velocity z
velocity z gaugevelocity z+2.51 within cohort, log-slope +0.028/wk.0+2.51
velocity z
+2.51 σ
slope
+0.028/wk
log-slope +0.028/wk
citation z Citation source: not measured.
direct-dependents z Direct-dependents axis: outside the frozen panel; not measured.
cohort
5778
systems measured
weekly commits
2.9
Development velocity axis: measured.
total citations
n/a
Citation source: not measured.
momentum
81.3
percentile p86
commit heatmap, last 26 weeks2.9/wk
weekly commits, 26 weeks26 weeks of commits, peak 12 in a week, 20 active weeks, 88 total.week 1: 0 commitsweek 2: 0 commitsweek 3: 2 commitsweek 4: 2 commitsweek 5: 12 commitsweek 6: 0 commitsweek 7: 0 commitsweek 8: 2 commitsweek 9: 5 commitsweek 10: 2 commitsweek 11: 6 commitsweek 12: 6 commitsweek 13: 5 commitsweek 14: 11 commitsweek 15: 0 commitsweek 16: 3 commitsweek 17: 3 commitsweek 18: 2 commitsweek 19: 2 commitsweek 20: 7 commitsweek 21: 0 commitsweek 22: 2 commitsweek 23: 5 commitsweek 24: 5 commitsweek 25: 2 commitsweek 26: 4 commits
weeks
26
peak/wk
12
active
20
total
88
citations by yearCitation source: not measured.

SAELens holds an Evidaxis momentum score of 81.3 of 100 on methodology m3, snapshot 2026-09-26, measured within the Unassigned (AI-v1 census) cohort (n = 5778). Axis coverage: 1 of 3 axes measurable. Gate: not computable — history 1 of 4 weekly observations

Derived signals

second-order reads, computed from the published series

Three signals ship when the commit series is statistically sufficient; the rest are held in a reserved state until the data supports them. A reserved signal shows its reason, never a fabricated number. How these are computed.

recency-weighted swing trailing 13-week vs prior 39-week log-slope ratio -0.60, regime recent slope sign differs from prior window. prior slope -0.018, recent slope +0.011 per week. -0.018prior 39w+0.011recent 13w-0.60×
swing
-0.60×
regime
recent slope sign differs from prior window
windows
13w vs 39w
snapshot 1 of 1 · · m3
commit-axis Sharpe log-linear slope over residual std, value -0.013 with 95% CI -0.036 to +0.009, 50 degrees of freedom. CI spans zero.0-0.01395% CI -0.036, +0.009-0.036+0.009
sharpe
-0.013
95% ci
-0.036, +0.009
dof
50
snapshot 1 of 1 · · m3
commit changepoint52 weekly commit points. No significant changepoint detected (|delta slope| within the noise floor).no significant changepoint
changepoint
none detected
snapshot 1 of 1 · · m3
code-leads-citation lag reserved

reserved: citation series too short / axis absent for cross-correlation

status
reserved
value
insufficient data
snapshot 1 of 1 · · m3
axis alpha vs cohort reserved

reserved: cohort N too small for regression (power ~0)

status
reserved
value
insufficient data
snapshot 1 of 1 · · m3
gate ETA reserved

reserved: needs snapshot history (1 snapshot exists)

status
reserved
value
insufficient history
snapshot 1 of 1 · · m3
methodology gate snapshot 1 of 1 · · m3
commit weeks
52
citation years
0
shipped
3
reserved
3

shipped

  • recency-swing
  • commit-sharpe
  • commit-changepoint

reserved

  • code-leads-citation-lag
  • axis-alpha
  • gate-eta
snapshot 1 of 1 · · m3

Measurement states

SAELens is under weekly measurement. History: 1 of 4 weekly observations. Development velocity axis: measured. Citation source: not measured. Direct-dependents axis: outside the frozen panel; not measured. Gate: not computable — history 1 of 4 weekly observations

Sources

decoderesearch/SAELens development-velocity axis

Others in Unassigned (AI-v1 census)

0xDeCA10B Unassigned (AI-v1 census)
1 of 3 axes measurable
51
p64
vel +0.05 cit no axis deps no axis
axis dials
+0.05 n/a n/a
10x Unassigned (AI-v1 census)
1 of 3 axes measurable
50
p49
vel +0.01 cit no axis deps no axis
axis dials
+0.01 n/a n/a
1Cat-vLLM Unassigned (AI-v1 census)
1 of 3 axes measurable
88
p96
vel +3.02 cit no axis deps no axis
axis dials
+3.02 n/a n/a
3D-convolutional-speaker-recognition Unassigned (AI-v1 census)
1 of 3 axes measurable
51
p59
vel +0.04 cit no axis deps no axis
axis dials
+0.04 n/a n/a
3D-ResNets-PyTorch Unassigned (AI-v1 census)
1 of 3 axes measurable
50
p39
vel -0.03 cit no axis deps no axis
axis dials
-0.03 n/a n/a
3DDFA Unassigned (AI-v1 census)
1 of 3 axes measurable
50
p39
vel -0.03 cit no axis deps no axis
axis dials
-0.03 n/a n/a

Full Unassigned (AI-v1 census) cohort →

Direct-dependents momentum (deps.dev)

Direct-dependents axis: outside the frozen panel; not measured.

Coverage state
out_of_panel
Cohort z
no axis
OLS slope
n/a
Theil-Sen slope
n/a
Latest direct dependents
n/a
Confirmed-clean points
n/a
Reconstructed history points
n/a
As-of partition
n/a
Fragility veto
n/a
Rising vote
no

Source: deps.dev (Google), CC-BY 4.0. Modified: aggregated to system-level counts and momentum scores.

Axis definition · Snapshot axis correlations

entity_id e_HX71294B3G3 methodology m3 snapshot 9d2fe956adbc period 2026-w39 record JSON ↓ source snapshot

Score derived from public data on Evidaxis methodology m3, never edited by hand. Cite as: “Evidaxis, SAELens, entity e_HX71294B3G3, snapshot 2026-w39.”

Durable reference (format-independent): urn:evidaxis:claim:e_HX71294B3G3:m3:2026-09-26